Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
RugnirViking
9 months ago
|
parent
|
context
|
favorite
| on:
Fresh evidence of ChatGPT’s political bias: study
LLMs are deterministic though? like with 0 temprature you always get the same output (temprature is literally injected randomness because by default they are "too" deterministic)
enterprise_cog
9 months ago
[–]
A 0 temp LLM is just an autocomplete. Not even spicy.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: